Wege (Fotokopie, Mikrokopie) zu vervielfältigen.

(Mathematik und Informatik) der

lativitätstheorie (ART). Dabei geht es um die Frage, ob und in welcher Weise

The accomplishment of this dissertation would not have been possible without the contribution of many individuals, to whom I want to express my appreciation and gratitude. First of all, I want to gratefully acknowledge my supervisor, Prof. Dr. Bernd Freisleben, for his persistent support and encouragement. His academic guidance and thorough insights helped me to find my own way in the world of research. I wish to express my gratitude to Prof. Dr. Wolfgang Wiechert for the fruitful technical discussions we had and for the insights he provided to me in the field of metabolic engineering and systems biology. My acknowledgement also goes to Prof. Dr. Bernhard Seeger and Prof. Dr. Eyke Hüllermeier for serving in my dissertation committee. The research work presented in this thesis was financially supported by the Deutsche Forschungsgemeinschaft (SPP 1063, Teilprojekt FR 791/8-1) and by Deutscher Akademischer Austauschdienst (DAAD, Stability Pact for

This thesis presents a method for automatic on-line color calibration of soccer-playing robots. It was developed to automate the color calibration process of the FU-Fighters Mid-Size robots, which play in the RoboCup Middle-Size League. Although the method was implemented on soccer-playing robots, it could also be used in other applications where colors need to be mapped to symbolic colors (calibrated). The method requires geometrical models of the objects whose colors are to be calibrated. In the implementation presented here, a model of the field-lines in world coordinates, and one of the ball in image coordinates was used. This made calibration of 4 distinct symbolic colors possible: Field (green), ball (orange), yellow goal (yellow) and blue goal (blue). The method accomplishes this without making any specific assumption about the color of the field, ball, or goals except that they are of roughly homogeneous distinct colors, and that the field-lines are bright relative to the field. The calibration works by localizing the robot(without using color information), then growing

Hiermit versichere ich, dass ich die vorliegende Diplomarbeit selbständig verfasst und keine anderen als die angegebenen Quellen und Hilfsmittel verwendet habe.

of a generic quality of service measurement and monitoring architecture

derCarl-von-OssietzkyUniversitat zurErlangungdesDoktorgrades desFachbereichsInformatik derNaturwissenschaften Dissertation

amFachbereichMathematikundInformatik derFreienUniversitätBerlin Eingereichtam:

Machine learning is an area of computer science concerned with the study of algorithms that reveal patterns and rules from data sets. Genomic profiles describe alterations of a genome, like copy number variations. Cancer often originates from a combination of genomic alterations. In this thesis, I consider machine learning and its application to genomic profiles. The main aspects of this work can be summarised as follows: First, I discuss several machine learning methods, with particular regard to genomic profiles, and then develop a special loss function for survival data. Next, I introduce a framework to find aberration patterns associated with a particular tumour type or disease state. This workflow starts with pre-processing, feature selection and discretisation of genomic profiles, includes strategies to deal with missing values and provides a multi-resolutional ana-lysis. Then, training and analysis of a classifier is performed. Additionally, I introduce an explanation component that emphasizes impor-